ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:

20 results for “Multimodal Large Language Models”

CS papers only

Hybrid search: Keyword + semantic, ranked by combined score.ⓘ

Want pure semantic search? Try claim verification →

cs.CRcs.AIMar 30, 2026

Adversarial Attacks on Multimodal Large Language Models: A Comprehensive Survey

Bhavuk Jain, Sercan Ö. Arık, Hardeo K. Thakur

This survey provides a comprehensive taxonomy and vulnerability-centric analysis of adversarial attacks targeting Multimodal Large Language Models (MLLMs), offering an explanatory framework for enhanc…

View →
cs.CVcs.CLcs.LGEmpiricalRecentAug 11, 2026

MultiModal Code-Switching: Interleaving Visual Objects into Language for Explicit Object-Level Alignment

Changhao Xiang, Shangyu Xing, Zhen Wu, Jianbing Zhang +1 more

This paper introduces MultiModal Code-Switching (MMCS), a new pretraining paradigm for multimodal large language models that provides explicit object-level supervision and improves visual grounding an…

View →
cs.IRcs.CVEmpiricalRecentJun 27, 2026

Multimodal Graph RAG for Long-range Visually Rich Document Understanding

Yi-Cheng Wang, Chu-Song Chen

This paper proposes a multimodal graph-based approach for constructing knowledge graphs from visually rich documents to improve multimodal question answering.

View →
cs.CLcs.AIRecentMay 30, 2026

MLLM-Microscope: Unlocking Hidden Structure Within Multimodal Large Language Models

Ravil Mussabayev, Rustam Mussabayev

The paper introduces MLLM-Microscope, a system that analyzes the internal structure of multimodal large language models (MLLMs), finding that modality fusion significantly impacts the linearity and di…

View →
cs.CLcs.AIcs.LGEmpiricalRecentJun 26, 2026

Do Speech Emphasis Models Generalize across Languages and Emotions?

Megan Wei, Deepali Aneja, Jiaqi Su, Yunyun Wang +2 more

This paper introduces MMEE, a multilingual and multi-emotion corpus for emphasis detection, and evaluates two state-of-the-art models under various settings.

View →
cs.CLcs.LGcs.SDEmpiricalRecentJun 21, 2026

Interleaved Speech Language Models Latently Work In Text

Talia Sternberg, Gallil Maimon, Yossi Adi

This paper analyzes speech-text interleaved language models and reveals that they go through an implicit transcription phase in which spoken words become decodable as text in intermediate layers.

View →
cs.CVcs.AIcs.MMEmpiricalRecentJul 10, 2026

Scalable Visual Pretraining for Language Intelligence

Yiming Zhang, Zhonghan Zhao, Wenwei Zhang, Haiteng Zhao +12 more

This paper presents the benefits of visual pretraining for foundation model intelligence, outperforming text-only pretraining on multiple backbones and benchmarks.

View →
eess.AScs.CLcs.SDEmpiricalRecentJun 24, 2026

Evaluating Japanese Dialect Robustness Across Speech and Text-based Large Language Models

Tomoya Mizumoto, Yusuke Fujita, Hao Shi, Lianbo Liu +2 more

This paper investigates the dialectal robustness of large language models and speech language models using Japanese dialects.

View →
eess.AScs.SDEmpiricalRecentSep 23, 2026

The Second MLC-SLM Challenge: Multilingual Conversational Speech Diarization, Recognition, and Understanding

Bingshen Mu, Mingchen Shao, Zhennan Lin, Liumeng Xue +6 more

The paper summarizes the Interspeech2026 Multilingual Conversational Speech Language Model Challenge and presents the results and insights from the challenge.

View →
cs.IREmpiricalRecentJun 18, 2026

Stellar: Scalable Multimodal Document Retrieval for Natural Language Queries

Yuxiang Guo, Zhonghao Hu, Yuren Mao, Yuhang Liu +4 more

This paper presents Stellar, a scalable multimodal document retrieval framework that reduces memory overhead and query latency without compromising retrieval effectiveness.

View →
cs.CLcs.SDEmpiricalRecentJun 10, 2026

UR-BERT: Scaling Text Encoders for Massively Multilingual TTS Through Universal Romanization and Speech Token Prediction

Sangmin Lee, Eekgyun Ahn, Woongjib Choi, Hong-Goo Kang

This paper proposes a Romanized transcription-based text-to-speech encoder for multilingual TTS systems that can handle 495 languages.

View →
cs.LGcs.CLEmpiricalRecentJun 17, 2026

Structured Inference with Large Language Gibbs

Sanghyeok Choi, Henry Gouk, Esmeralda S. Whitammer

The paper proposes Large Language Gibbs, a scheme for structured probabilistic inference using conditional distributions of large language models as transition operators.

View →
cs.CLcs.AIeess.ASRecentMay 31, 2026

PolySpeech-100: A Large-Scale Benchmark for Speech Understanding Across 100+ Languages and Dialects

Sicheng Yang, Shulan Ruan, Shiwei Wu, Yu Liu +3 more

PolySpeech-100 introduces a massive, multi-lingual benchmark covering 110 linguistic variants to rigorously test Speech-LLMs, demonstrating that open-source models struggle with low-resource languages…

View →
eess.ASDatasetRecentJul 15, 2026

Dialogs: a studio-quality expressive conversational Russian speech corpus for dialog assistants

Ilya Shigabeev, Ilya Latyshev

The paper introduces Dialogs, a new Russian conversational speech corpus with high-quality recordings, segmented utterances, and expressive prosody labels.

View →
cs.CLcs.AIeess.ASEmpiricalRecentJul 24, 2026

MEUSLI: a Multilingual Projector for LLM-based ASR and Beyond

Lorenzo Concina, Seraphina Fong, Marco Matassoni, Alessio Brutti

MEUSLI introduces an open-source multilingual projector family linking a Whisper encoder with LLMs, enabling end-to-end ASR in 28 European languages and supporting multilingual speech translation and…

View →
cs.SDcs.CLeess.ASEmpiricalRecentOct 20, 2026

Uncovering Audio-Text Alignment in Large Audio-Language Models through Cross-Modal Concept Neurons

Tzu-Quan Lin, Chih-Kai Yang, Yi-Cheng Lin, Hao Tang +1 more

This paper investigates how audio and text representations are integrated in large audio-language models.

View →
cs.LGcs.CVEmpiricalRecentOct 19, 2026

Text-to-Image Generative Modeling Without Language Pretraining

Keshigeyan Chandrasegaran, Yue Zhao, Armin W. Thomas, Ehsan Adeli +4 more

The paper presents a new text-to-image generation model, Halcyon, that can be trained from scratch without internet-scale language pretraining.

View →